N-GRAM CLASSIFICATION IN SOCIAL MEDIA MESSAGES

    公开(公告)号:US20190155946A1

    公开(公告)日:2019-05-23

    申请号:US15817505

    申请日:2017-11-20

    Applicant: Colossio, Inc.

    Inventor: Joseph A. Jaroch

    Abstract: Systems and a method for n-gram classification of social media content are provided. In one or more aspects, a system includes a network interface to receive the social media content from a social media network. The social media content includes a string of characters. A processor can process the string of characters by parsing the string of characters and resolving encodings by removing markup characters from the string of characters. The processor further extracts non-text sub strings from the string of characters, and tokenizes the string of characters into separate words.

    TRACKING THE MENTAL ACUITY OF AN ELECTRONIC DEVICE USER

    公开(公告)号:US20190129766A1

    公开(公告)日:2019-05-02

    申请号:US15794660

    申请日:2017-10-26

    Applicant: Colossio, Inc.

    Inventor: Joseph A. Jaroch

    Abstract: A method including retrieving, from an operating system of a client device, a timestamp associated with a physical action on an input device coupled with the client device, is provided. The method includes tagging the timestamp with an action metadata of an application running in the client device, the physical action being associated with the application, and forming an aggregated dataset comprising the timestamp and the action metadata. The method also includes associating an acuity value to the timestamp based on the aggregated dataset, and modifying a display of an application output to indicate the acuity value within the application. A system and a non-transitory, computer readable medium storing instructions to perform the method are also provided.

    AUTOMATED QUANTITATIVE ASSESSMENT OF TEXT COMPLEXITY

    公开(公告)号:US20190108215A1

    公开(公告)日:2019-04-11

    申请号:US15729098

    申请日:2017-10-10

    Applicant: Colossio, Inc.

    Inventor: Joseph A. Jaroch

    Abstract: Various aspects of the subject technology relate to systems, methods, and machine-readable media for automated quantitative assessment of text complexity. A system may include processing at least one body of text in a text-based query using a natural language processing engine. The processed text may include sub-blocks of text in a predetermined sequence size such as an n-gram. The system may compare reference bases to the processed text, where each reference base is associated with a different natural language. The system determines which of the reference bases has a highest number of matching words within the body of text, and thereby identifies the reference base as the source language of the supplied text. The system then determines an average complexity score for n-gram using a quantitative assessment engine. The system then applies a readability score to the body of text based on the average complexity scores of the n-grams.

    Sliding window pattern matching for large data sets

    公开(公告)号:US11086865B2

    公开(公告)日:2021-08-10

    申请号:US15921303

    申请日:2018-03-14

    Applicant: Colossio, Inc.

    Inventor: Joseph A. Jaroch

    Abstract: Methods for providing sliding window pattern matching for large data sets are provided. In one aspect, a method includes accessing a data store comprising a plurality of records each associated with a timestamp and at least one type of measurement value. The method also includes retrieving a multidimensional search query spanning a defined length of time. The method also includes iteratively searching the plurality of records using the multidimensional search query, which is successively reduced in size. Each iteration uses an optimization function to determine similarity values. Once a match with an optimal confidence value is found, the iterative search can be halted. The method also includes outputting a prediction result selected from the plurality of records having associated timestamps after the candidate match assigned to the optimal confidence value. Systems and machine-readable media are also provided.

    SLIDING WINDOW PATTERN MATCHING FOR LARGE DATA SETS

    公开(公告)号:US20190286730A1

    公开(公告)日:2019-09-19

    申请号:US15921303

    申请日:2018-03-14

    Applicant: Colossio, Inc.

    Inventor: Joseph A. Jaroch

    Abstract: Methods for providing sliding window pattern matching for large data sets are provided. In one aspect, a method includes accessing a data store comprising a plurality of records each associated with a timestamp and at least one type of measurement value. The method also includes retrieving a multidimensional search query spanning a defined length of time. The method also includes iteratively searching the plurality of records using the multidimensional search query, which is successively reduced in size. Each iteration uses an optimization function to determine similarity values. Once a match with an optimal confidence value is found, the iterative search can be halted. The method also includes outputting a prediction result selected from the plurality of records having associated timestamps after the candidate match assigned to the optimal confidence value. Systems and machine-readable media are also provided.

    Automated quantitative assessment of text complexity

    公开(公告)号:US10417335B2

    公开(公告)日:2019-09-17

    申请号:US15729098

    申请日:2017-10-10

    Applicant: Colossio, Inc.

    Inventor: Joseph A. Jaroch

    Abstract: Various aspects of the subject technology relate to systems, methods, and machine-readable media for automated quantitative assessment of text complexity. A system may include processing at least one body of text in a text-based query using a natural language processing engine. The processed text may include sub-blocks of text in a predetermined sequence size such as an n-gram. The system may compare reference bases to the processed text, where each reference base is associated with a different natural language. The system determines which of the reference bases has a highest number of matching words within the body of text, and thereby identifies the reference base as the source language of the supplied text. The system then determines an average complexity score for n-gram using a quantitative assessment engine. The system then applies a readability score to the body of text based on the average complexity scores of the n-grams.

    INSTRUMENTED RESEARCH AGGREGATION SYSTEM
    27.
    发明申请

    公开(公告)号:US20190258740A1

    公开(公告)日:2019-08-22

    申请号:US15900076

    申请日:2018-02-20

    Applicant: Colossio, Inc.

    Inventor: Joseph A. Jaroch

    Abstract: A system and methods for instrumented research aggregation of content are provided. Crawling processes having multiple instances and multiple IP regions per instance are distributed to multiple processors for a variety of designated content sources and feeds. An aggregated content database is generated and trigger parameters and/or subscriptions are set in relation to the database. As new content is posted to the designated content sources and feeds, a full copy of the content document is downloaded and stored, raw text is extracted from the stored document and stored, and content analysis is performed on the text document and the results are stored. For any new content that trips the set triggers/subscription parameters, a notification is sent to the associated users with a link to the stored document and an abstract of relevant text.

    COMPRESSION AND MANIPULATION-RESISTANT FUZZY HASHING

    公开(公告)号:US20190245692A1

    公开(公告)日:2019-08-08

    申请号:US15888613

    申请日:2018-02-05

    Applicant: Colossio, Inc.

    Inventor: Joseph A. Jaroch

    Abstract: Systems and a method for compression and manipulation-resistant fuzzy hashing are provided. In one or more aspects, a system includes a network interface to receive an image object from a network, and a processor to process the image object. The processing includes generating pairs of random numbers using a hash of pixel data of the image object as a seed. The processing further includes identifying a number of coordinate pairs, within image pixels of the image object, such that coordinate values of each coordinate pair of the identified coordinate pairs approximately matches one pair of the random numbers. A number of first entropy values associated with first sub-areas corresponding to the identified coordinate pairs are determined. An anchor point within the image pixels is identified that has coordinate values corresponding to a sub-area that is associated with a highest entropy value among the determined first entropy values.

    ONE-TIME-PAD ENCRYPTION
    29.
    发明申请

    公开(公告)号:US20190104114A1

    公开(公告)日:2019-04-04

    申请号:US15722663

    申请日:2017-10-02

    Applicant: Colossio, Inc.

    Inventor: Joseph A. Jaroch

    Abstract: Methods for secure communications using one-time pad encryption are provided. In one aspect, a method includes generating and sharing, via proximity inter-device communication, unique device codes on each of multiple devices to be paired or grouped together, intermixing the device codes to generate a one-time pad code, generating a random block of data based on the one-time pad code, persisting the one-time pad code and random block of data over each device, and encrypting/decrypting messages between the paired or grouped devices. Systems and machine-readable media are also provided.

    INFORMATION DENSITY OF DOCUMENTS
    30.
    发明申请

    公开(公告)号:US20190056913A1

    公开(公告)日:2019-02-21

    申请号:US15680788

    申请日:2017-08-18

    Applicant: Colossio, Inc.

    Inventor: Joseph A. Jaroch

    Abstract: A method that includes receiving a document, the document including multiple data units arranged in a sequence, is provided. The method includes separating a fragment from the sequence by identifying a delimiter that includes one of a start or an end of the fragment, separating a data unit from the fragment by identifying a second delimiter, determining a fragment rank based on a frequency score of the data unit within the fragment, and placing the fragment in a sorted list based on the fragment rank including multiple fragments. The method includes forming a modified document including at least a top fragment from the sorted list, the top fragment having a top fragment rank greater than a user selected rank and providing the modified document to the user. A system and a non-transitory, computer readable medium storing instructions to perform the method are also provided.

Patent Agency Ranking